Spherical CNNs tackle 3D data analysis, especially spherical images.
problem Learning problems involving spherical images, like omnidirectional vision and molecular regression.
method Defined spherical cross-correlation, developed a generalized FFT for efficient computation.
result Demonstrated spherical CNNs' effectiveness in 3D model recognition and atomization energy regression.
Graph-based CNN for spherical data with equivariance.
problem Efficiently learning from non-uniformly distributed spherical data.
method Discretized sphere as graph, graph convolutions, equivariance using Defferrard's graph neural network.
result Good performance on rotation-invariant learning problems.
DeepSphere improves spherical CNNs by balancing efficiency and rotation equivariance.
problem Designing efficient and rotation-equivariant convolutional layers for spherical data.
method Graph-based approach to represent spherical data, focusing on the number of vertices and neighbors.
result DeepSphere achieves state-of-the-art performance and demonstrates efficiency and flexibility.
Generalizes CNNs on homogeneous spaces like Euclidean and spherical surfaces.
problem Classifying and understanding equivariant CNNs on homogeneous spaces.
method Develops a theory for equivariant maps between field spaces of given types.
result Equivariant kernels correspond to the most general kind of equivariant linear maps.
Gauge equivariant CNNs improve image segmentation and climate pattern analysis.
problem Improving image segmentation and climate pattern analysis on non-Euclidean surfaces.
method Developed gauge equivariant convolutional neural networks (gCNNs) for icosahedral surfaces.
result Significant improvements in image segmentation and climate pattern analysis.
CeCNN predicts SE and AL from UWF images, improving myopia screening.
problem Predicting axial length and spherical equivalence from UWF fundus images.
method Copula-enhanced Convolutional Neural Network (CeCNN) for multiresponse regression.
result CeCNN improves prediction of SE and AL compared to baseline CNNs.
Paper reduces Hausdorff Distance in medical image segmentation.
problem Reduction of Hausdorff Distance in medical image segmentation.
method Three novel loss functions for training CNNs to estimate and reduce HD.
result Approximately 18-45% reduction in HD without degrading other performance metrics.
Group equivariant neural networks simplify complex tasks with group representation theory.
problem Challenging tasks requiring input transformations like rotations.
method Group representation theory, non-commutative harmonic analysis, differential geometry.
result A neural network is group equivariant if and only if it has a convolutional structure.
Characterization of lung nodules as benign or malignant is one of the most important tasks in lung cancer diagnosis, staging and treatment planning. While the variation in the appearance of the nodules remains large, there is a need for a fast and robust computer aided system. In this work, we propose an end-to-end tra…
Coordinate-independent convolutions on manifolds avoid reference frame ambiguity.
problem Applying convolutions on non-Euclidean manifolds without reference frame ambiguity.
method Developed coordinate-independent and gauge-equivariant convolutions on Riemannian manifolds.
result Coordinate-independent convolutions are equivariant under local gauge transformations.
Unified geometric scattering model for measure spaces.
problem Improving CNNs for non-Euclidean data.
method Unified geometric scattering model for measure spaces.
result Unified model includes previous work and applies to more general settings.
The study classifies singularities of spherical orthotomic curves.
problem Classifying singularities of spherical orthotomic curves.
method Defining spherical orthotomic curves and classifying their singularities.
result Singularities of spherical orthotomic curves are classified.
Paper introduces spherical knot mosaics for knot and link invariants.
problem Representing knots on a sphere with tiles.
method Tiling a 2-sphere with 11 knot mosaic tiles to define new invariants.
result New knot invariants derived from spherical mosaic tiling.
Study predicts lens performance using neural networks.
problem Predicting visual acuity from lens designs.
method Used a CNN to classify Landolt Cs and validate its ability to predict VA from induced defocus.
result Validation showed consistent offset of +0.20 logMAR from simulated VA, comparable to clinical repeatability.
Study geodesics on spherical polyhedra, estimating their number.
problem Counting simple closed geodesics on spherical polyhedra.
method Examined regular spherical octahedra, cubes, and tetrahedra.
result Estimated the number of simple closed geodesics on spherical polyhedra.
The abstract proves spherical surface decompositions with conical singularities.
problem Decomposing surfaces with spherical metrics and conical singularities.
method Geometric triangulations and irreducible components of standard shapes.
result Spherical polygons, including half-spherical concave polygons, can be arbitrarily complicated.
V-CNN improves CNN performance in network intrusion detection.
problem Applying CNN directly to non-image data leads to poor performance.
method Integrates data visualization before CNN modeling.
result Significantly outperforms other studies in network intrusion detection.
Study spherical curves with curvature dependent on distance to a great circle.
problem Understanding spherical curves with curvature dependent on distance to a great circle.
method Introducing spherical angular momentum, characterizing known curves, finding new families, and obtaining arc length parametrizations.
result New families of spherical curves with intrinsic equations in elementary or Jacobi elliptic functions.
Study calculates eigenvalues and eigenfunctions for spherical triangles and finds fundamental gap behavior.
problem Understanding eigenvalues and gaps in spherical triangles.
method Explicit computation of Dirichlet eigenvalues and eigenfunctions for spherical lunes and triangles.
result Fundamental gap of spherical triangles increases as the angle of the lune decreases.
New findings show fundamental group is not audible in spherical space forms.
problem Isospectral spherical space forms with non-cyclic fundamental groups.
method Revisited and found new examples of spherical space forms.
result Fundamental group is not audible among spherical space forms.
Existence and uniqueness of spherical helicoidal surfaces in 3-sphere via spherical curves.
problem Existence and uniqueness of spherical helicoidal surfaces in 3-sphere.
method Continuous function of distance to axis, spherical angular momentum of spherical curves.
result Existence and uniqueness theorem for spherical helicoidal surfaces in 3-sphere.
The reductivity of a spherical curve represents how reduced the spherical curve is. It is unknown if there exists a spherical curve whose reductivity is four. In this paper we give an unavoidable set for spherical curves with reductivity four by considering 4-gons.
The reductivity of a spherical curve is the minimal number of a local transformation called an inverse-half-twisted splice required to obtain a reducible spherical curve from the spherical curve. It is unknown if there exists a spherical curve whose reductivity is four. In this paper, an unavoidable set of configuratio…
The paper improves inequalities for nearly spherical sets using quermassintegrals.
problem Improving inequalities for nearly spherical sets.
method Establishing quantitative Alexandrov-Fenchel inequalities for quermassintegrals.
result Lower bounds on the (k,m)-isoperimetric deficit found using spherical deviation and asymmetry. The paper classifies Landsberg spherically symmetric Finsler metrics in various dimensions.
problem Investigating compatibility conditions on spherically symmetric Finsler metrics.
method Using the inverse problem of calculus of variations, the paper focuses on Landsberg and Berwald types.
result All Landsberg spherically symmetric manifolds in higher dimensions are either Riemannian or have specific geodesic spray formulas.
We show that we can obtain a reducible spherical curve from any non-trivial spherical curve by four or less inverse-half-twisted splices, i.e., the reductivity, which represents how reduced a spherical curve is, is four or less. We also discuss unavoidable sets of tangles for spherical curves.
For a convex body on the Euclidean unit sphere the spherical convex floating body is introduced. The asymptotic behavior of the volume difference of a spherical convex body and its spherical floating body is investigated. This gives rise to a new spherical area measure, the floating area. Remarkably, this floating area…
Study on spherical CR manifolds with non-trivial Chern classes.
problem Understanding Chern classes in spherical CR manifolds.
method Construction and proof of constraints on Chern classes.
result Topological obstruction to spherical CR structures on contact manifolds.
DELIMIT PyTorch enhances deep learning for diffusion imaging.
problem Applying deep learning to spherical diffusion imaging data.
method Added spherical harmonic interpolation and local convolution layers to PyTorch.
result Deep learning can now be applied conveniently to diffusion imaging data.
PGF kernels analyze spherical data using generalized RBF kernels.
problem Analysis of spherical data.
method Introduced PGF kernels and a semi-parametric learning algorithm.
result PGF kernels generalize RBF kernels for spherical data.
The paper examines properties of spherical Finsler metrics, proving their semi-C-reducibility and conditions for vanishing mean stretch curvature.
problem Analyzing curvature properties of spherical Finsler metrics.
method Proving semi-C-reducibility and finding conditions for vanishing mean stretch curvature.
result Conditions for a general spherically symmetric Finsler metric to have vanishing mean stretch curvature.
Enhances CNN generalization in early learning with hierarchical transfer.
problem Improving CNN generalization in limited training time for real-time applications.
method Hierarchical transfer CNN framework combining shallow and cloud CNNs.
result Significant improvement in testing accuracy, up to 20% for CIFAR-10.
Classifies involutions on spherical 3-manifolds.
problem Classifying involutions on spherical 3-manifolds.
method Geometric approach to conjugacy classification.
result Insights into topological properties of involutions.
The paper classifies spherically symmetric Finsler metrics as Berwaldian or Riemannian.
problem Classifying spherically symmetric Finsler metrics.
method Proving all spherically symmetric Landsberg surfaces are Berwaldian and modifying the classification of spherically symmetric Finsler metrics.
result All Berwald spherically symmetric metrics of dimension n≥3 are Riemannian or given by a specific formula. New approximative kernels improve PDE-G-CNNs for geometric deep learning.
problem Inaccurate approximations of exact kernels in PDE-G-CNNs.
method Developed new approximative kernels that work regardless of spatial anisotropy.
result New kernels provide better error estimates and maintain reflectional symmetries.
Study on spherical Finsler metrics with isotropic curvature rigidity.
problem Characterizing and understanding spherically symmetric Finsler metrics with isotropic E-curvature. method Provided the correct formula for mean Berwald curvature, established differential equations for projective and dual flatness, and derived a rigidity result.
result Rigidity result on spherically symmetric Finsler metrics with isotropic E-curvature. CNNs improve medical image classification with few samples.
problem Classifying medical images with limited training data.
method Transfer learning using CNNs, representation extraction, and a novel metric for performance prediction.
result CNN-based transfer learning outperforms feature-based methods with high correlation to test set performance.
The paper creates spherical CR structures for Whitehead link surgeries.
problem Creating spherical CR structures for Dehn surgeries of the Whitehead link.
method Applying spherical CR Dehn surgery theorem to deform Ford domains.
result Infinitely many Dehn surgeries of the Whitehead link complement with spherical CR structures.
Paper develops invariants for spherical curves using chord diagrams.
problem Developing invariants for spherical curves under local moves.
method Using based chord diagrams and local moves from Reidemeister moves.
result Invariants include both classical and new spherical curve invariants.
In this paper we consider the spherical slant helices in R3. More- over, we show how could be obtained to a spherical slant helix and we give some spherical slant helix examples in Euclidean 3-space.
The paper characterizes spherically symmetric metrics with scalar curvature.
problem Characterizing spherically symmetric metrics with scalar curvature.
method Established a curvature compatibility condition on spherically symmetric Finsler metrics and constructed a Berwald frame.
result Characterized spherically symmetric metrics with scalar curvature.
The study proves spherical polygon analogs of curve theorems, finding bounds on intersections and inflections.
problem Finding bounds on intersections and inflections for spherical polygons.
method Adapting smooth curve theorems to spherical polygons using discrete tools.
result Proves discrete analogs of four-vertex theorems for spherical polygons.
AT-CNNs show improved shape recognition over texture recognition.
problem Understanding adversarial training's impact on CNNs' feature learning.
method Systematic qualitative and quantitative approaches to interpret AT-CNNs.
result Adversarial training reduces texture bias and improves shape recognition.
Euler explored spherical geometry using trigonometric formulae and solid geometry methods.
problem Developing trigonometric formulae for spherical geometry.
method Used calculus of variations and classical solid geometry methods.
result Established trigonometric formulae and computed spherical triangle areas.
New formula for spherical polygon area via prequantization.
problem Traditional area formula for spherical polygons requires measuring angles.
method Uses prequantization to create a new formula that doesn't require angle measurement.
result New formula applicable to a wider range of degenerate curves and polygons.
A spherical polyhedron surface is a triangulated surface obtained by isometric gluing of spherical triangles. For instance, the boundary of a generic convex polytope in the 3-sphere is a spherical polyhedron surface. This paper investigates these surfaces from the point of view of inner angles. A rigidity result is obt…
Recently we initiated the study of spherical T-duality for spacetimes that are principal SU(2)-bundles. In this paper, we extend spherical T-duality to spacetimes that are oriented non-principal SU(2)-bundles. There are several interesting new examples in this case and a new phenomenon appearing in the non-principal ca…
Paper learns an explainer to interpret CNN features without annotations.
problem Interpreting complex features in CNNs without labeled data.
method Unsupervised learning of an explainer to decompose and reconstruct feature maps.
result Explainer learns to reconstruct CNN features without losing information.